© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 70822
    Prev
    Next
    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     сайт
    -0.07
     Trip
    -0.07
     Bank
    -0.07
     статус
    -0.07
     ఆ
    -0.07
     وث
    -0.07
    σή
    -0.07
     trape
    -0.07
    Trip
    -0.07
     ней
    -0.07
    POSITIVE LOGITS
     included
    0.08
    -------↵↵
    0.08
    	rt
    0.07
    ẫu
    0.07
     정말
    0.07
    ược
    0.07
    १२
    0.07
    _placeholder
    0.07
    ////↵
    0.07
    结束
    0.07
    Activations Density 0.019%

    No Known Activations